About

I build LLM-based systems that read the traces people leave on their smartphones, such as screen text and other sensor data, to understand how they behave and feel, and to offer personalized support.

My research sits at the intersection of human-computer interaction, ubiquitous computing and psychology, and asks how large language models can make humans more human: helping them understand themselves, care for their wellbeing and connect with one another.

My PhD at the University of Melbourne is advised by Prof. Vassilis Kostakos, Prof. Jorge Goncalves and Dr. Hong Jia. Before that, I received an M.S. in Computer Science from Northwestern University and a B.S. in Information Sciences and Technology from Pennsylvania State University, where I was a Schreyer Honors Scholar. From June to July 2026 I was a visiting researcher in Prof. Koji Yatani's Interactive Intelligent Systems Lab at the University of Tokyo. I am a member of ASPIRE-MWI, an international research community on data-driven mental well-being.

Outside research, I write stories for tabletop role-playing games and host the sessions as game master. I have also trained in Muay Thai for three years and fought several times in the ring.

News

  • 2026/08Our paper showing that LLMs rate human happiness higher than humans do was accepted at npj Digital Public Health (in press).
  • 2026/06Began a two-month visiting research stay at the University of Tokyo, hosted by Prof. Koji Yatani.

Publications

  1. Fang, L., Zhang, T., Brockmeier, L. C., Zhang, S., Fei, R., Ma, Y., Teng, S., D'Alfonso, S., Koval, P., Jia, H., Goncalves, J., & Kostakos, V. (in press). Large language models rate human happiness higher than humans do. npj Digital Public Health.
  2. Ma, Y., Govers, J., Fang, L., Zhang, S., Hu, Y. O., Yi, X., & Goncalves, J. (2026). “Black Mirror?”: Public sensemaking of AI-powered lifelogging wearables. In Companion of the 2026 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2026 ACM International Symposium on Wearable Computers (UbiComp/ISWC '26). ACM.arXiv
  3. Fang, L., Zhang, S., Jia, H., Goncalves, J., & Kostakos, V. (2024). ScreenTK: Seamless detection of time-killing moments using continuous mobile screen text and on-device LLMs. In Companion of the 2024 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp '24). ACM. https://doi.org/10.1145/3675094.3677547arXiv
  4. Zhang, T., Zhang, S., Fang, L., Jia, H., Kostakos, V., & D'Alfonso, S. (2024). AutoJournaling: A context-aware journaling system leveraging MLLMs on smartphone screenshots. In Proceedings of the 30th Annual International Conference on Mobile Computing and Networking (MobiCom '24), EIFCom Workshop (pp. 2347–2352). ACM. https://doi.org/10.1145/3636534.3698122Best Presentation Award
  5. Zhang, S., Ma, Y., Fang, L., Jia, H., D'Alfonso, S., & Kostakos, V. (2024). Enabling on-device LLMs personalization with smartphone sensing. In Companion of the 2024 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp '24). ACM. https://doi.org/10.1145/3675094.3677545arXiv
  6. Calvillo, J., Fang, L., Cole, J., & Reitter, D. (2020). Surprisal predicts code-switching in Chinese-English bilingual text. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.emnlp-main.330

Teaching and service

Head Tutor, Mobile Computing2026The University of Melbourne
Tutor2024 – presentMobile Computing, Media Computation, UI Development; Statistical Learning (Melbourne Business School)
Social Chair, EIFCOM 20262026International Workshop on Mobile Systems with Efficient Foundation Models
ReviewerACM CHI; ACM IMWUT; PLOS Digital Health